このエントリーをはてなブックマークに追加
ID 30021
FullText URL
Author
Ninomiya, Akira
Horiuchi, Tadashi
Konishi, Tadataka
Baba, Mitsuru
Abstract

This paper applies our state construction method by ART neural network to robot navigation problems. Agents in this paper consist of ART neural network and contradiction resolution mechanism. The ART neural network serves as a mean of state recognition which maps stimulus inputs to a certain state and state construction which creates a new state when a current stimulus input cannot be categorized into any known states. On the other hand, the contradiction resolution mechanism (CRM) uses agents' state transition table to detect inconsistency among constructed states. In the proposed method, two kinds of inconsistency for the CRM are introduced: "Different results caused by the same states and the same actions" and "Contradiction due to ambiguous states." The simulation results on the robot navigation problems confirm the effectiveness of the proposed method

Keywords
Adaptive State Construction
ART Neural Network
Reinforcement Learning
Note
Digital Object Identifier: 10.1109/ICSMC.2001.973484
Published with permission from the copyright holder. This is the institute's copy, as published in Systems, Man, and Cybernetics, 2001 IEEE International Conference on, 7-10 Oct. 2001, Vol. 3, Pages 1436-1441.
Publisher URL:http://dx.doi.org/10.1109/ICSMC.2001.973484
Copyright © 2001 IEEE. All rights reserved.
Published Date
2001-10
Publication Title
Systems
Volume
volume3
Start Page
1436
End Page
1441
Content Type
Journal Article
language
英語
Refereed
True
DOI
Submission Path
industrial_engineering/35